检索结果-内蒙古大学图书馆

Predicting User Preferences with Neural Network Learning to Rank Method 5

Predicting User Preferences with Neural Network Learning to ...

5th IEEE International Conference on Information Technology, Information systems and Electrical Engineering, ICITISEE 2021

作者： Qomariyah, Nunung Nurul Fajar, Ahmad Nurul Bina Nusantara University Faculty Of Computing And Media Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program-Master Of Information Systems Management Information Systems Management Department Jakarta11480 Indonesia

ISBN: (纸本)9781665401968

User preference learning has been around for many years. This is a common problem arise in e-commerce system, where the companies need to understand their customers in order to sell the correct products to their target customers. The user preference is also needed in the movie domain area, as the film companies who produce the movie also need to understand how the customers value their movie products, whether the market like it or not. This can help them to predict the best components for the future movie. In order to produce the recommendation to the customer, we can show a list of item in a correct order, sorted from the most relevant/the most liked one to the most irrelevant item. In this paper, we utilize the Learning to Rank (LTR) approach from information retrieval domain area to learn the user preference in recommender system domain. We applied LTR with pairwise approach from the two most popular algorithms in this area, i.e. RankNet and LambdaRank, on 25, 345 user ratings from 5, 000 movie dataset and evaluate both algorithms. We used a Neural Network architecture as the learning mechanism. We also measuring the speed performance of the two algorithms. © 2021 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Wound Reconstruction using Point Descriptors: A Comparative Study

Three-Dimensional Wound Reconstruction using Point Descripto...

引用

Annual IEEE Symposium on Computer-Based Medical systems

作者： José R. A. Souto Fellipe M. C. Barbosa Bruno M. Carvalho Graduate Program in Systems and Computing Federal University of Rio Grande do Norte Natal Brazil Department of Informatics and Applied Mathematics Federal University of Rio Grande do Norte Natal Brazil

Precise measurements of chronic wound areas are very important for measuring the efficacy of different treatments, since it provides a clear picture of the chosen treatment evolution. The most used techniques still in use for measuring the wound areas involve manual measuring, paper scales and/or acetate tracing, with each health professional possibly measuring the wounds in slightly different ways, specially when dealing with the wound's depth. Thus, it is common to observe inconsistent wound area estimations by different health workers on the same wounds. Moreover, the measuring process requires direct contact with the wound, increasing the contamination and infection risks, besides possibly causing discomfort for the patient. An alternative that has already been proved successful is the use of Structure from Motion (SfM) to recover three-dimensional representations of a wound's surface and estimate that area. In this work, we analyze the effectiveness of several widely used point descriptors (BRIEF, DRINK, FREAK, ORB, SIFT and SURF) in the SfM wound reconstruction task when applied to real images of realistic synthetic wounds made of latex placed on different areas of the body. The results showed that SIFT, SURF and DRINK produced better area estimates. Since the execution time is a factor, we selected DRINK as the standard descriptor for our system, since it is approximately 9.3 and 4.9 times faster than SIFT and SURF, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expanding PyAFAR: A Novel Privacy-Preserving Infant AU Detector

Expanding PyAFAR: A Novel Privacy-Preserving Infant AU Detec...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Itir Onal Ertugrul Saurabh Hinduja Maneesh Bilalpur Daniel S. Messinger Jeffrey F. Cohn Department of Information and Computing Sciences Utrecht University Utrecht The Netherlands Department of Psychology University of Pittsburgh Pittsburgh PA USA Intelligent Systems Program University of Pittsburgh Pittsburgh USA Department of Psychology University of Miami Miami FL USA

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

We enhance PyAFAR 1 1 Code will be available on: https:\\***/PyAFARI, an open source, Python-based library for facial action unit detection by introducing a privacy-protected infant AU detector. To prevent reconstruction of the training images, we train the infant AU detector by extracting histogram of gradients (HoG) features and using an efficient Light Gradient Boosting Machine (LightGBM) classifier. Models are trained with two large, well-annotated databases. The performance of our approach is comparable to previously developed deep models that have not been released due to privacy concerns. Our models are available for use and further fine-tuning, contributing to the advancement of facial action unit detection.

关键词： Training Gold Privacy Histograms Face recognition Detectors Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Acceptance Analysis of IWB systems in Education using UTAUT2 Model: The Moderating Role of Perceived Technological Innovations

Acceptance Analysis of IWB Systems in Education using UTAUT2...

引用

IEEE International Conference on Automatic Control and Intelligent systems (I2CACIS)

作者： Noelyn M. De Jesus Eltimar T. Castro Cory Antonio Buyan College of Informatics & Computing Sciences Batangas State University Batangas Phlippines Graduate Program Department Technological Institute of the Philippines Manila Philippines Business Technology Ballard Power Systems Burnaby Canada

Interactive Whiteboard (IWB) systems are increasingly being used to replace traditional whiteboards in educational activities, making them more efficient and interesting for both teachers and students. However, no studies have been conducted to investigate how age, educational level, and employment status can impact the adoption and usage of IWB systems in the educational setting. The study aims to analyze the acceptance and the influencing factors on faculty members’ intention and usage behavior towards IWB systems in teaching, utilizing the Modified-Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) model. 135 faculty members from various colleges and departments across Batangas State University ARASOF-Nasugbu Campus were surveyed and data was analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) through SmartPLS software for hypotheses testing. The results of the study indicate that faculty members’ behavioral intention to use interactive whiteboard systems in teaching is positively influenced by performance expectancy and social influence. Moreover, facilitating conditions and habit positively impact usage behavior. This study, therefore, concludes that there is significant roles of performance expectancy and social influence as well as the moderating effect of age on the behavioral intention to use interactive whiteboard (IWB) systems in education. Furthermore, the study confirms that effort expectancy, hedonic motivation, and status as moderating variables significantly influence faculty members’ usage behavior when using IWB systems in teaching.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Double-SP Method to Enhance Privacy and Security of Smart City Applications 10

Double-SP Method to Enhance Privacy and Security of Smart Ci...

引用

17th INDIACom;2023 10th International Conference on computing for Sustainable Global Development, INDIACom 2023

作者： Bahbouh, Nour Mahmoud Hakami, Abdulelah Alhussain Hassan Aljohani, Yaser Mohammed Sen, Adnan Ahmed Abi Alkhodre, Ahmad Alsughayyir, Aeshah Granada University Department of Information and Communication Sciences Granada Spain Saudi Electronic University Al-Madinah Saudi Arabia YasRef Program Yanbu Saudi Arabia Computing and Information Technology Islamic University Al-Madinah Saudi Arabia Islamic University Faculty of Computer and Information Systems Al-Madinah Saudi Arabia College of Computer Science and Engineering Taibah University Al-Madinah Saudi Arabia

ISBN: (纸本)9789380544472

Smart cities promise a lot of well-being to their users in all areas of life through millions of applications and services. Smart services rely heavily on collecting data and the preferences of users. But on the dark side, the users' information is posed to threat and penetration during transmission or stored far in the clouds. Depending on encryption only is not sufficient if the attacker has strong resources or if the attacker is the service provider (SP) itself. In addition, changing data before sending is not a practical solution in many systems because of the adverse impact on the quality of a main service. This research presented a new idea to address the issue of protection. The proposed method enhanced the privacy and security of users' data without affecting the accuracy of service. The core of the suggested solution relies on a knowledge base of services that are managed by experts. Also, the solution depends on fog nodes to measure the level of security and privacy of users' queries without delay. Moreover, the fog nodes manage contact with SPs. Finally, the proposed method divided the SP into two, one for user queries and the other for user data. The simulation and analytical discussion on a practical case in smart cities demonstrated the superiority of the proposed approach over previous methods in the level of protection by maintaining the quality of services, and the resistance to attacks. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Determining environmental indicators related to the propagation of contagious diseases and health issues: A Systematic Literature Review

Determining environmental indicators related to the propagat...

引用

Iberian Conference on Information systems and Technologies (CISTI)

作者： Janeth Domínguez Portillo Laura M. Rodríguez Peralta Paulo N. M. Sampaio Eldman de Oliveira Nunes Faculty of Information Technologies and Data Science Universidad Popular Autónoma del Estado de Puebla (UPAEP) México Graduate Program in Computing and Systems University of Salvador (UNIFACS) Salvador Bahia Brazil

The environmental indicators provide significant information in order to describe the state of a phenomenon, environment or area [1]. This paper addresses the indicators present in the air and their relationship in the accommodation and transmission of viruses, as well as how these environmental indicators can lead to health problems. Therefore, the main goal of this work is to review the scientific contributions in the literature in order to determine and select the potential environmental indicators present in indoor environments which have an impact on the health of people who work and live within these spaces. For this purpose, we carried out a Systematic Literature Review (SLR) related to environmental monitoring, COVID-19, Internet of things, air pollution and environmental indicators within indoor spaces. This SLR allowed us to identify indicators that according to their level of presence can represent a high risk for people’s health. Therefore, the process of planning, conducting and reporting the Systematic Literature Review enabled us not only to identify some environmental indicators, but also their corresponding monitoring advantages and disadvantages, and multiple perspectives and approaches of each contribution in the literature. Further on, this study will be the basis for the proposal of an automatic and intelligent platform based on Internet of Things for monitoring indoor environments in order to detect high risk levels for the contamination of contagious diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Retinitis Pigmentosa

Early Detection of Retinitis Pigmentosa

引用

IEEE International Conference on Intelligent computing and Information systems (ICICIS)

作者： Adham Mohammed El Gazoly Karma Yasser Ismail Mahmoud Ahmed El-Tohamy Ali Ahmed Hassan Omar Mohammed Hamed Mohammed Maryam Nabil Al-Berry Hasnaa Sayed Abdo Mohammed Yousra Samir Al Amir Bioinformatics Program Information Systems Department Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Scientific Computing Department Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt

Retinitis pigmentosa (RP) is a debilitating inherited retinal disorder that affects a significant number of individuals worldwide. Existing diagnostic methods have limitations in detecting early-stage RP and they highlight the need for using additional imaging modalities. In this paper, a groundbreaking approach for RP diagnosis is proposed using three imaging modalities and a CNN-based classification model achieving 97.7% accuracy. The proposed model demonstrates superior performance compared to previous work as it achieves higher accuracy. A segmentation model was also proposed to segment pigment spots and provide doctors with effective monitoring of the disease. The proposed segmentation model outperforms previously used methods by achieving 99.61% accuracy and higher values in most of the performance metrics, including specificity, precision, and Area Under Curve (AUC). The Segmentation and classification models were integrated into a web application providing a user-friendly and intuitive tool for RP diagnosis and paving the way for more accessible and effective diagnostic tools. This innovative approach democratizes healthcare by making RP diagnosis affordable and accessible to more people and improving the speed of clinical decision-making.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring User Experience of Massive Open Online Courses (MOOCs): A Case Study of Millennial Learners in Jakarta, Indonesia 2020

Exploring User Experience of Massive Open Online Courses (MO...

引用

9th International Conference on Educational and Information Technology, ICEIT 2020

作者： Nurhudatiana, Arfika Caesarion, Alixia Shafira Business Information Systems Program Information Systems Department Faculty of Computing Media Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781450375085

Over the past years, millions of internet users have been taking online classes offered by Massive Open Online Course (MOOC) platforms. This research investigated the user experience of two popularly used MOOC platforms, Coursera and Udemy, by referring to the seven dimensions of user experience (UX) honeycomb including usefulness, usability, desirability, findability, accessibility, credibility, and value. The research was conducted among 77 millennials in Jakarta, Indonesia, covering not only active users of Coursera and Udemy, but also new users with no experience in MOOCs. The exploratory research employed a user participatory evaluation strategy where study participants were given a task to perform learning activities in either Coursera or Udemy platform and provide qualitative and quantitative feedbacks. Qualitative data were gathered through think-aloud approach and semi-structured post-walkthrough interviews, while quantitative data were collected through questionnaire. In overall, all study participants agreed that Coursera and Udemy were very useful and easy to use, and Coursera was perceived to have stronger credibility. Majority of the study participants preferred Udemy for its better findability, affordable pricing, and wide range of course options. It was emphasized that MOOC platform was easier to use for people already familiar with online learning. Therefore, it was recommended that MOOC platforms should improve the learnability of the user interface design so that new users could learn to use MOOC platforms more easily. © 2020 ACM.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Measuring the contribution of multiple model representations in detecting adversarial instances

arXiv

引用

arXiv 2021年

作者： Steinberg, Daniel Munro, Paul Intelligent Systems Program University of Pittsburgh School of Computing and Information University of Pittsburgh

Deep learning models have been used for a wide variety of tasks. They are prevalent in computer vision, natural language processing, speech recognition, and other areas. While these models have worked well under many scenarios, it has been shown that they are vulnerable to adversarial attacks. This has led to a proliferation of research into ways that such attacks could be identified and/or defended against. Our goal is to explore the contribution that can be attributed to using multiple underlying models for the purpose of adversarial instance detection. Our paper describes two approaches that incorporate representations from multiple models for detecting adversarial examples. We devise controlled experiments for measuring the detection impact of incrementally utilizing additional models. For many of the scenarios we consider, the results show that performance increases with the number of underlying models used for extracting representations. Code is available at https://***/dstein64/multi-advdetect. Copyright © 2021, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Visualizing representations of adversarially perturbed inputs

arXiv

引用

arXiv 2021年

作者： Steinberg, Daniel Munro, Paul Intelligent Systems Program University of Pittsburgh School of Computing and Information University of Pittsburgh

It has been shown that deep learning models are vulnerable to adversarial attacks. We seek to further understand the consequence of such attacks on the intermediate activations of neural networks. We present an evaluation metric, POP-N, which scores the effectiveness of projecting data to N dimensions under the context of visualizing representations of adversarially perturbed inputs. We conduct experiments on CIFAR-10 to compare the POP-2 score of several dimensionality reduction algorithms across various adversarial attacks. Finally, we utilize the 2D data corresponding to high POP-2 scores to generate example visualizations. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：